unit8co/darts

Write an `NBEATSExplainer` class for the interpretable version

Open

#1,270 创建于 2022年10月9日

在 GitHub 查看
 (1 评论) (0 反应) (0 负责人)Python (6,832 star) (762 fork)batch import
good first issueimprovement

描述

NBEATS has an "interpretable" mode where it decomposes the forecast in trend and seasonality. We should have a class NBEATSExplainer in darts.explainability which exposes these.

贡献者指南

技术栈
python
领域
machine learningdata
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-3 hours
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
fresh
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
Basic knowledge of NBEATS modelFamiliarity with darts library
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
50
研究方向
Examine the existing NBEATS implementation in darts (likely in darts.models.forecasting.nbeats) to understand how the interpretable mode decomposes forecasts into trend and seasonality components. Then, create a new class NBEATSExplainer in darts.explainability that exposes these components, following the patterns used by other explainer classes in the module. Consider reviewing any related discussions in issue comments for additional context.